© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151579
    Prev
    Next
    INDEX
    Explanations

    multilingual text processing

    np_acts-logits-general · gemini-2.5-flash-lite

    removing unnecessary words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    쇤
    0.50
     antisemit
    0.44
     diagonalization
    0.43
    ទ្រ
    0.43
    랬
    0.42
     actualizaciones
    0.42
     incontro
    0.42
    aufnahme
    0.41
     말고
    0.41
     rebuke
    0.41
    POSITIVE LOGITS
    UX
    0.49
     Machine
    0.49
     تیم
    0.48
     数据
    0.47
    ي
    0.47
    2
    0.46
     Sous
    0.46
    IR
    0.44
     نق
    0.43
     مط
    0.43
    Activations Density 0.001%

    No Known Activations